trainer_state.json

{
  "best_metric": 0.8594666666666667,
  "best_model_checkpoint": "./resnet_finetuned_models_dataset/CIFAR100/50_from_100/microsoft_resnet-101/model_idx_0821/checkpoints/checkpoint-1665",
  "epoch": 5.0,
  "eval_steps": 500,
  "global_step": 1665,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "grad_norm": 250.39715576171875,
      "learning_rate": 8.397114317029975e-05,
      "loss": 3.1005,
      "step": 333
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.6517333333333334,
      "eval_loss": 1.36312735080719,
      "eval_runtime": 13.3719,
      "eval_samples_per_second": 280.439,
      "eval_steps_per_second": 4.412,
      "step": 333
    },
    {
      "epoch": 2.0,
      "grad_norm": 91.09251403808594,
      "learning_rate": 6.75e-05,
      "loss": 0.8744,
      "step": 666
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.8098666666666666,
      "eval_loss": 0.6441528797149658,
      "eval_runtime": 12.9967,
      "eval_samples_per_second": 288.534,
      "eval_steps_per_second": 4.54,
      "step": 666
    },
    {
      "epoch": 3.0,
      "grad_norm": 126.88492584228516,
      "learning_rate": 4.5e-05,
      "loss": 0.5501,
      "step": 999
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.8368,
      "eval_loss": 0.5386564135551453,
      "eval_runtime": 12.9083,
      "eval_samples_per_second": 290.512,
      "eval_steps_per_second": 4.571,
      "step": 999
    },
    {
      "epoch": 4.0,
      "grad_norm": 108.04928588867188,
      "learning_rate": 2.250000000000001e-05,
      "loss": 0.4247,
      "step": 1332
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.8584,
      "eval_loss": 0.4718531668186188,
      "eval_runtime": 13.4895,
      "eval_samples_per_second": 277.995,
      "eval_steps_per_second": 4.374,
      "step": 1332
    },
    {
      "epoch": 5.0,
      "grad_norm": 95.98467254638672,
      "learning_rate": 6.028856829700258e-06,
      "loss": 0.3687,
      "step": 1665
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.8594666666666667,
      "eval_loss": 0.4697636663913727,
      "eval_runtime": 12.9892,
      "eval_samples_per_second": 288.701,
      "eval_steps_per_second": 4.542,
      "step": 1665
    }
  ],
  "logging_steps": 500,
  "max_steps": 1998,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 6,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 4.088214619776e+18,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}